{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T04:06:53Z","timestamp":1793419613092,"version":"4.5.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002729","name":"Anhui University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002729","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.patcog.2024.111053","type":"journal-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T16:24:10Z","timestamp":1727454250000},"page":"111053","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":15,"special_numbering":"C","title":["Temporal adaptive bidirectional bridging for RGB-D tracking"],"prefix":"10.1016","volume":"158","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1259-2111","authenticated-orcid":false,"given":"Ge","family":"Ying","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7593-1593","authenticated-orcid":false,"given":"Dawei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Ou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-9215","authenticated-orcid":false,"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2024.111053_b1","doi-asserted-by":"crossref","unstructured":"Song Yan, Jinyu Yang, Jani K\u00e4pyl\u00e4, Feng Zheng, Ale\u0161 Leonardis, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Depthtrack: Unveiling the power of rgbd tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10725\u201310733.","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"10.1016\/j.patcog.2024.111053_b2","series-title":"Rgbd object tracking: An in-depth review","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2024.111053_b3","doi-asserted-by":"crossref","unstructured":"Ugur Kart, Joni-Kristian Kamarainen, Jiri Matas, How to make an rgbd tracker?, in: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018.","DOI":"10.1007\/978-3-030-11009-3_8"},{"key":"10.1016\/j.patcog.2024.111053_b4","doi-asserted-by":"crossref","unstructured":"Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kamarainen, Jiri Matas, Object tracking by reconstruction with view-specific discriminative correlation filters, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1339\u20131348.","DOI":"10.1109\/CVPR.2019.00143"},{"issue":"3","key":"10.1016\/j.patcog.2024.111053_b5","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","article-title":"Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos","volume":"21","author":"Liu","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2024.111053_b6","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"7825","article-title":"DAL: A deep depth-aware long-term tracker","author":"Qian","year":"2021"},{"key":"10.1016\/j.patcog.2024.111053_b7","unstructured":"Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian Kamarainen, Luka \u010cehovin Zajc, Ondrej Drbohlav, Alan Lukezic, Amanda Berg, et al., The seventh visual object tracking vot2019 challenge results, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019."},{"key":"10.1016\/j.patcog.2024.111053_b8","unstructured":"Matej Kristan, Ale\u0161 Leonardis, Ji\u0159\u00ed Matas, Michael Felsberg, Roman Pflugfelder, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Martin Danelljan, Luka \u010cehovin Zajc, Alan Luke\u017ei\u010d, Ondrej Drbohlav, et al., The eighth visual object tracking VOT2020 challenge results, in: Computer Vision\u2013ECCV 2020 Workshops: Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16, 2020, pp. 547\u2013601."},{"key":"10.1016\/j.patcog.2024.111053_b9","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"9391","article-title":"Visual adapt for RGBD tracking","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2024.111053_b10","doi-asserted-by":"crossref","unstructured":"Jinyu Yang, Zhe Li, Feng Zheng, Ales Leonardis, Jingkuan Song, Prompting for multi-modal tracking, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 3492\u20133500.","DOI":"10.1145\/3503161.3547851"},{"key":"10.1016\/j.patcog.2024.111053_b11","doi-asserted-by":"crossref","unstructured":"Jiawen Zhu, Simiao Lai, Xin Chen, Dong Wang, Huchuan Lu, Visual prompt multi-modal tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.patcog.2024.111053_b12","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2024.111053_b13","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"670","article-title":"Tsdm: Tracking by siamrpn++ with a depth-refiner and a mask-generator","author":"Zhao","year":"2021"},{"key":"10.1016\/j.patcog.2024.111053_b14","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778."},{"key":"10.1016\/j.patcog.2024.111053_b15","series-title":"European Conference on Computer Vision","first-page":"341","article-title":"Joint feature learning and relation modeling for tracking: A one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.patcog.2024.111053_b16","series-title":"Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.patcog.2024.111053_b17","doi-asserted-by":"crossref","unstructured":"Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg, Atom: Accurate tracking by overlap maximization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4660\u20134669.","DOI":"10.1109\/CVPR.2019.00479"},{"key":"10.1016\/j.patcog.2024.111053_b18","doi-asserted-by":"crossref","unstructured":"Goutam Bhat, Martin Danelljan, Luc Van Gool, Radu Timofte, Learning discriminative model prediction for tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6182\u20136191.","DOI":"10.1109\/ICCV.2019.00628"},{"key":"10.1016\/j.patcog.2024.111053_b19","doi-asserted-by":"crossref","unstructured":"Xin Chen, Bin Yan, Jiawen Zhu, Dong Wang, Xiaoyun Yang, Huchuan Lu, Transformer tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8126\u20138135.","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.patcog.2024.111053_b20","doi-asserted-by":"crossref","unstructured":"Bin Yan, Houwen Peng, Jianlong Fu, Dong Wang, Huchuan Lu, Learning spatio-temporal transformer for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10448\u201310457.","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"10.1016\/j.patcog.2024.111053_b21","series-title":"Rgbd object tracking: An in-depth review","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2024.111053_b22","series-title":"BMVC","first-page":"01","article-title":"Real-time RGB-d tracking with depth scaling kernelised correlation filters and occlusion handling","volume":"Vol. 3","author":"Camplani","year":"2015"},{"issue":"8","key":"10.1016\/j.patcog.2024.111053_b23","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1109\/TCYB.2017.2740952","article-title":"Robust fusion of color and depth data for RGB-d target tracking using adaptive range-invariant depth models and spatio-temporal consistency constraints","volume":"48","author":"Xiao","year":"2017","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2024.111053_b24","doi-asserted-by":"crossref","unstructured":"Lichao Zhang, Abel Gonzalez-Garcia, Joost Van De Weijer, Martin Danelljan, Fahad Shahbaz Khan, Learning the model update for siamese trackers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4010\u20134019.","DOI":"10.1109\/ICCV.2019.00411"},{"key":"10.1016\/j.patcog.2024.111053_b25","doi-asserted-by":"crossref","unstructured":"Ning Wang, Wengang Zhou, Jie Wang, Houqiang Li, Transformer meets tracker: Exploiting temporal context for robust visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 1571\u20131580.","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"10.1016\/j.patcog.2024.111053_b26","doi-asserted-by":"crossref","unstructured":"Ziang Cao, Ziyuan Huang, Liang Pan, Shiwei Zhang, Ziwei Liu, Changhong Fu, Tctrack: Temporal contexts for aerial tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14798\u201314808.","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"10.1016\/j.patcog.2024.111053_b27","unstructured":"Tianrui Hui, Zizheng Xun, Fengguang Peng, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu, Bridging search region interaction with template for rgb-t tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13630\u201313639."},{"key":"10.1016\/j.patcog.2024.111053_b28","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.patcog.2024.111053_b29","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","article-title":"Got-10k: A large high-diversity benchmark for generic object tracking in the wild","volume":"43","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2024.111053_b30","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.patcog.2024.111053_b31","doi-asserted-by":"crossref","unstructured":"Alan Lukezic, Ugur Kart, Jani Kapyla, Ahmed Durmush, Joni-Kristian Kamarainen, Jiri Matas, Matej Kristan, Cdtb: A color and depth visual object tracking dataset and benchmark, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 10013\u201310022.","DOI":"10.1109\/ICCV.2019.01011"},{"key":"10.1016\/j.patcog.2024.111053_b32","doi-asserted-by":"crossref","unstructured":"Haojie Zhao, Junsong Chen, Lijun Wang, Huchuan Lu, Arkittrack: a new diverse dataset for tracking using mobile RGB-D data, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 5126\u20135135.","DOI":"10.1109\/CVPR52729.2023.00496"},{"key":"10.1016\/j.patcog.2024.111053_b33","doi-asserted-by":"crossref","unstructured":"Yutao Cui, Cheng Jiang, Limin Wang, Gangshan Wu, Mixformer: End-to-end tracking with iterative mixed attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13608\u201313618.","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10.1016\/j.patcog.2024.111053_b34","doi-asserted-by":"crossref","unstructured":"Christoph Mayer, Martin Danelljan, Goutam Bhat, Matthieu Paul, Danda Pani Paudel, Fisher Yu, Luc Van Gool, Transforming model prediction for tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8731\u20138740.","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"10.1016\/j.patcog.2024.111053_b35","article-title":"Self-supervised learning for RGB-d object tracking","author":"Zhu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111053_b36","unstructured":"Matej Kristan, Ji\u0159\u00ed Matas, Ale\u0161 Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Hyung Jin Chang, Martin Danelljan, Luka Cehovin, Alan Luke\u017ei\u010d, et al., The ninth visual object tracking vot2021 challenge results, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 2711\u20132738."},{"key":"10.1016\/j.patcog.2024.111053_b37","unstructured":"The Visual Object Tracking RGBD Challenge 2022, in: Proceedings of the VOT2022 Workshop on the Visual Object Tracking Challenge, 2022, Author names, Publisher, Location."},{"key":"10.1016\/j.patcog.2024.111053_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110626","article-title":"Multi-modal interaction with token division strategy for RGB-T tracking","author":"Cai","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111053_b39","doi-asserted-by":"crossref","unstructured":"Tianlu Zhang, Hongyuan Guo, Qiang Jiao, Qiang Zhang, Jungong Han, Efficient rgb-t tracking via cross-modality distillation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 5404\u20135413.","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"10.1016\/j.patcog.2024.111053_b40","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3396289","article-title":"Towards modalities correlation for RGB-T tracking","author":"Hu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324008045?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324008045?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T15:00:58Z","timestamp":1731250858000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320324008045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":40,"alternative-id":["S0031320324008045"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111053","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Temporal adaptive bidirectional bridging for RGB-D tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111053","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"111053"}}